rmania

import pprint
import requests
import json

pc_list = ['1069KJ', '1058NH', '1057PV'] 
# or 4-digit postal codes
pc_list = ['1069', '1058', '1057'] 
num_url = 'https://api.data.amsterdam.nl/bag/nummeraanduiding/'  

# totaal resultaten opvangen in results list..

rmania

# script with 2 ways to push to postgresql database
import pandas as pd
import psycopg2 
import logging
import configparser
from sqlalchemy import create_engine

# config parser 
config = configparser.RawConfigParser()
config.read('auth.conf')

rmania

from functools import partial
import pyproj as proj
from shapely.ops import transform
from shapely.geometry import mapping, shape
import json

def rd2wgsGeojson(geojson):
   # convert geojson from RD new to WSG84
   reprojection = partial(proj.transform,
                          # Source coordinate system

rmania

from collections import OrderedDict
def json_to_csv(input_f, output_f):
    """ Convert JSON to CSV """

    input_data = json.load(input_f, object_pairs_hook=OrderedDict)

    if isinstance(input_data, list):
        list_of_dicts = input_data
        fieldnames = list_of_dicts[0].keys()

rmania

############ ExtraTreesRegressor , TimeSeriesSplit
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error

# Model selection
etr = ExtraTreesRegressor(n_estimators = 100, n_jobs=-1)

# Predict, TimeSeriesSplit
tscv = TimeSeriesSplit(n_splits=5)
results = []

rmania

import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import Imputer

# some functions executing some basic preprocessing steps for ml
predict_cols = ['x']
feature_cols = list(set(df.columns) - set(predict_cols) - {'source'})

# PREPROCESSING STEPS

rmania

from pyspark.sql import functions as F

# remap one columns value F.when, otherwise
df = df.withColumn('colx', F.when(F.col('prefix')=='EZS', 'EZY').otherwise(F.col('prefix'))) 

# remap one column with double when condition. f.i. Reassign pier_in 'D' to DN/DSN based on incoming gate number
luggage_df = (luggage_df.withColumn('pier_in', 
                 F.when((F.col('vop_in').isin(DS))  & (F.col('pier_in') == 'D'), 'DS')
                  .when((F.col('vop_in').isin(DNS)) & (F.col('pier_in') == 'D'), 'DNS')
                  .otherwise(F.col('pier_in')))

rmania

# modify color of yticklabels for the current axes
[i.set_color("red") for i in plt.gca().get_yticklabels()]

# get all tweakable parameters of 'ytick' etc..
[(param, value) for param, value in plt.rcParams.items() if 'ytick' in param]

# get the yticklabel texts
[item.get_text() for item in axi.get_yticklabels()]

#change label display parameters like fontsize

rmania

# Often when reading in a ShapeFile from Basemap, you'll get: "ValueError: readshapefile can only handle 2D shape types"
# A trick can be to convert your geometry in your GeoPandas Dataframe and restoring the new flattened 2D geometry
# series back into a shapefile and try again.

# edit from http://stackoverflow.com/questions/33417764/basemap-readshapefile-valueerror  

from shapely.geometry import Polygon, MultiPolygon, shape, Point
import geopandas as gp
def convert_3D_2D(geometry):
    '''